Next Article in Journal
Phytoestrogenic Effects of Blackcurrant Anthocyanins Increased Endothelial Nitric Oxide Synthase (eNOS) Expression in Human Endothelial Cells and Ovariectomized Rats
Next Article in Special Issue
Synthesis, Biological and In Silico Evaluation of Pure Nucleobase-Containing Spiro (Indane-Isoxazolidine) Derivatives as Potential Inhibitors of MDM2–p53 Interaction
Previous Article in Journal
Structural Comparison of Enterococcus faecalis and Human Thymidylate Synthase Complexes with the Substrate dUMP and Its Analogue FdUMP Provides Hints about Enzyme Conformational Variabilities
Open AccessArticle

Heterologous Machine Learning for the Identification of Antimicrobial Activity in Human-Targeted Drugs

1
Department of biochemistry and structural biology, Instituto de Fisiología Celular, UNAM, Mexico City 04510, Mexico
2
Computer Science Department, CICESE Research Center, Ensenada, Baja California 22860, Mexico
3
Department of genetics, Instituto de Fisiología Celular, UNAM, Mexico City 04510, Mexico
*
Author to whom correspondence should be addressed.
Academic Editor: Julio Caballero
Molecules 2019, 24(7), 1258; https://doi.org/10.3390/molecules24071258
Received: 1 February 2019 / Revised: 9 March 2019 / Accepted: 14 March 2019 / Published: 31 March 2019
(This article belongs to the Special Issue Computational Methods for Drug Discovery and Design)
The emergence of microbes resistant to common antibiotics represent a current treat to human health. It has been recently recognized that non-antibiotic labeled drugs may promote antibiotic-resistance mechanisms in the human microbiome by presenting a secondary antibiotic activity; hence, the development of computer-assisted procedures to identify antibiotic activity in human-targeted compounds may assist in preventing the emergence of resistant microbes. In this regard, it is worth noting that while most antibiotics used to treat human infectious diseases are non-peptidic compounds, most known antimicrobials nowadays are peptides, therefore all computer-based models aimed to predict antimicrobials either use small datasets of non-peptidic compounds rendering predictions with poor reliability or they predict antimicrobial peptides that are not currently used in humans. Here we report a machine-learning-based approach trained to identify gut antimicrobial compounds; a unique aspect of our model is the use of heterologous training sets, in which peptide and non-peptide antimicrobial compounds were used to increase the size of the training data set. Our results show that combining peptide and non-peptide antimicrobial compounds rendered the best classification of gut antimicrobial compounds. Furthermore, this classification model was tested on the latest human-approved drugs expecting to identify antibiotics with broad-spectrum activity and our results show that the model rendered predictions consistent with current knowledge about broad-spectrum antibiotics. Therefore, heterologous machine learning rendered an efficient computational approach to classify antimicrobial compounds. View Full-Text
Keywords: machine-learning; antimicrobial peptide; non-peptidic antimicrobial compound; antimicrobial activity machine-learning; antimicrobial peptide; non-peptidic antimicrobial compound; antimicrobial activity
Show Figures

Graphical abstract

MDPI and ACS Style

Nava Lara, R.A.; Aguilera-Mendoza, L.; Brizuela, C.A.; Peña, A.; Del Rio, G. Heterologous Machine Learning for the Identification of Antimicrobial Activity in Human-Targeted Drugs. Molecules 2019, 24, 1258.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
  • Externally hosted supplementary file 1
    Link: http://bis.ifc.unam.mx:8080/ironbios/heteroml/
    Description: File S1: Script to execute the best model to predict antimicrobials on FDA-approved drugs Table S1(A,B,C,D,E): Training sets in ARF format for TrOnlyPeptides Table S2(A,B,C,D,E): Training sets in ARFF format for TrNPCC1 Table S3(A,B,C,D,E): Training sets in ARFF format for TrNPCC2 Table S4(A,B,C,D,E): Training sets in ARFF format for TrNPCC3 Table S5(A,B,C,D,E): Training sets in ARFF format for TrNPCC4 Table S6(A,B,C,D,E,F,G,H,H,I,J,K,L): Training sets in ARFF format for TrHeterologous1 Table S7(A,B,C,D,E): Training sets in ARFF format for TrHeterologous2 Table S8(A,B,C,D,E): Training sets in ARFF format for TrHeterologous3 Table S9(A,B,C,D,E): Training sets in ARFF format for TrHeterologous4 Table S10(A,B,C,D,E): Testing sets in ARF format for TeOnlyPeptides Table S11(A,B,C,D,E): Testing sets in ARF format for TeNPCC1 Table S12(A,B,C,D,E): Testing sets in ARF format for TeNPCC2 Table S13(A,B,C,D,E): Testing sets in ARF format for TeNPCC3 Table S14(A,B,C,D,E): Testing sets in ARF format for TeNPCC4 Table S15(A,B,C,D,E,F,G,H,I,J): Testing sets in ARF format for TeHetrelogous1 Table S16(A,B,C,D,E): Testing sets in ARF format for TeHetrelogous2 Table S17(A,B,C,D,E): Testing sets in ARF format for TeHetrelogous3 Table S18(A,B,C,D,E): Testing sets in ARF format for TeHetrelogous4 Table S19: Parameter values for all models tested Table S20: CScore values for all model tested Table S21: Best models algorithms and corresponding parameters Table S22: Discovery set
Back to TopTop